library(tidyverse)LEGO
Packages
We’ll use the tidyverse package for much of the data wrangling and visualization. The tidyverse package should be installed by now on your computer. If not, take again a look at the Set Up tutorial. You can load the tidyverse with the following command:
Data
The data is contained in the file lego.csv and can be found on Moodle in the folder Data files, Quarto files and Solutions to previous problem sets.
It is simulated data based on real prices for LEGO sales in 2018 in the United States. Names and hobbies have been randomly generated. The dataset contains the following variables.
| Variable | Description |
|---|---|
first_name |
First name of customer |
last_name |
Last name of customer |
age |
Age of customer |
phone_number |
Phone number of customer |
set_id |
Set ID of LEGO set purchased |
number |
Item number of LEGO set purchased |
theme |
Theme of LEGO set purchased |
subtheme |
Sub theme of LEGO set purchased |
year |
Year of purchase |
name |
Name of LEGO set purchased |
pieces |
Number of pieces of LEGOs in set purchased |
us_price |
Price of the set purchased in US Dollars |
quantity |
Quantity of LEGO set(s) purchased |
Solutions
Solution 1. Save the data and the starter file appropriately so the following code works.
lego <- read_csv("data/lego.csv")Remark: Don’t forget to remove eval: false or change it to eval: true.
Take a glimpse at the data.
lego# A tibble: 620 × 13
first_name last_name age phone_number set_id number theme subtheme year
<chr> <chr> <dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
1 Kimberly Beckstead 24 216-555-2549 24701 76062 DC C… Mighty … 2018
2 Neel Garvin 35 819-555-3189 25626 70595 Ninj… Rise of… 2018
3 Neel Garvin 35 819-555-3189 24665 21031 Arch… <NA> 2018
4 Chelsea Bouchard 41 <NA> 24695 31048 Crea… <NA> 2018
5 Chelsea Bouchard 41 <NA> 25626 70595 Ninj… Rise of… 2018
6 Chelsea Bouchard 41 <NA> 24721 10831 Duplo <NA> 2018
7 Bryanna Welsh 19 <NA> 24797 75138 Star… Episode… 2018
8 Bryanna Welsh 19 <NA> 24701 76062 DC C… Mighty … 2018
9 Caleb Garcia-Wide… 37 907-555-9236 24730 41115 Frie… <NA> 2018
10 Caleb Garcia-Wide… 37 907-555-9236 25611 21127 Mine… Minifig… 2018
# ℹ 610 more rows
# ℹ 4 more variables: name <chr>, pieces <dbl>, us_price <dbl>, quantity <dbl>Solution 2. In this sample, the first three common names of purchasers are “Jackson”, “Jacob” and “Joseph”.
lego |>
count(first_name) |>
arrange(desc(n))# A tibble: 211 × 2
first_name n
<chr> <int>
1 Jackson 13
2 Jacob 11
3 Joseph 11
4 Michael 10
5 Audrey 8
6 Connor 8
7 Kaitlyn 8
8 Lucas 8
9 Amanda 7
10 Joshua 7
# ℹ 201 more rowsSolution 3. Dropping the observations with NA subtheme:
lego <- lego |>
drop_na(subtheme)REMARK: Use the reduced dataset to answer the following questions.
Solution 4. The three most common themes are “Star Wars”, “Mixels” and “Gear”.
lego |>
group_by(theme) |>
mutate(quantity = sum(quantity)) |>
distinct(theme, quantity) |>
arrange(desc(quantity))# A tibble: 19 × 2
# Groups: theme [19]
theme quantity
<chr> <dbl>
1 Star Wars 117
2 Mixels 83
3 Gear 79
4 City 59
5 Ninjago 48
6 Bionicle 46
7 Friends 37
8 DC Comics Super Heroes 35
9 Nexo Knights 32
10 Marvel Super Heroes 30
11 Dimensions 24
12 Disney Princess 20
13 Minecraft 10
14 Architecture 10
15 Advanced Models 5
16 Duplo 5
17 Seasonal 4
18 Ghostbusters 3
19 Collectable Minifigures 3Within the theme “Mixels”, the most common subtheme is “Series 7”; within the theme “Star Wars”, the most common subtheme is “The Force Awakens”; within the theme “Gear”, the most common subtheme is “Tole-Play toys”.
lego |>
filter(theme %in% c("Star Wars", "Mixels", "Gear")) |>
group_by(subtheme) |>
mutate(quantity = sum(quantity)) |>
distinct(theme, subtheme, quantity) |>
arrange(desc(quantity))# A tibble: 28 × 3
# Groups: subtheme [28]
theme subtheme quantity
<chr> <chr> <dbl>
1 Mixels Series 7 30
2 Mixels Series 8 28
3 Mixels Series 9 25
4 Star Wars The Force Awakens 21
5 Star Wars Buildable Figures 18
6 Star Wars Episode V 15
7 Star Wars Battlefront 12
8 Star Wars MicroFighters 11
9 Gear Role-Play toys 11
10 Gear Stationery 11
# ℹ 18 more rowsSolution 5. Using the case_when() function, a new variable can be added. The case_when() function evaluates the arguments in order; here I have chosen to start with the highest age and let the function work the way through to the youngest age.
lego <- lego |>
mutate(
age_group =
case_when(
age >= 51 ~ "51 and over",
age >= 36 ~ "36 - 50",
age >= 26 ~ "26 - 35",
age >= 19 ~ "19 - 25",
age <= 18 ~ "18 and under"
)
) Solution 6. The age group “36-50” purchased the most lego sets, followed by the age age group “26-35” and “19-25”.
lego |>
group_by(age_group) |>
mutate(quantity = sum(quantity)) |>
distinct(age_group, quantity) |>
arrange(desc(quantity))# A tibble: 5 × 2
# Groups: age_group [5]
age_group quantity
<chr> <dbl>
1 36 - 50 232
2 26 - 35 193
3 19 - 25 119
4 51 and over 73
5 18 and under 33Solution 7. Replicaating the plot:
lego |>
filter(theme %in% c("Nexo Knights", "City", "Ninjago")) |>
ggplot(aes(x = theme, fill = age_group)) +
geom_bar() +
scale_fill_brewer(palette = "Set1") +
labs(
title = "Distribution of age within each of the three popular themes",
x = "Popular LEGO theme",
fill = "Age group"
)
Between the variables theme and age_group there seems to be some association (at least within this sample). If you adjust the position of the bar chart to “fill”, you can observe the different proportions of age groups within each theme. The proportion of “51 and over”s purchasing Ninjago sets is e.g. bigger than the same group purchasing City sets.
Solution 8. The age group 36-50 has spent the most money on lego with 9532.87 dollars.
lego |>
mutate(money_spent = quantity * us_price) |>
group_by(age_group) |>
summarise(age_group_spending = sum(money_spent)) |>
arrange(desc(age_group_spending))# A tibble: 5 × 2
age_group age_group_spending
<chr> <dbl>
1 36 - 50 7064.
2 26 - 35 4872.
3 19 - 25 3377.
4 51 and over 1877.
5 18 and under 809.Solution 9. The result shows 35 rows, thus there are 35 observations from the age group 36-50 that have been buying either a set from the Star Wars or the Ninjago theme.
lego |>
filter(age_group == "36 - 50", theme == "Star Wars" | theme == "Ninjago")# A tibble: 35 × 14
first_name last_name age phone_number set_id number theme subtheme year
<chr> <chr> <dbl> <chr> <dbl> <chr> <chr> <chr> <dbl>
1 Chelsea Bouchard 41 <NA> 25626 70595 Ninjago Rise of… 2018
2 Toni Borison 40 284-555-4560 25626 70595 Ninjago Rise of… 2018
3 Amanda Tronnier 45 317-555-7477 24959 75139 Star Wa… The For… 2018
4 Erik Brownrigg 44 <NA> 25621 70589 Ninjago Rise of… 2018
5 Cecilia Mauro 50 <NA> 25921 75157 Star Wa… Rebels 2018
6 Connor Padilla 36 441-555-6534 24797 75138 Star Wa… Episode… 2018
7 Caroline Holstein 38 318-555-7894 24798 75140 Star Wa… The For… 2018
8 Caroline Holstein 38 318-555-7894 24959 75139 Star Wa… The For… 2018
9 Taylor Allen 41 760-555-8123 25923 75147 Star Wa… Origina… 2018
10 Katherine Beck 45 209-555-7105 24959 75139 Star Wa… The For… 2018
# ℹ 25 more rows
# ℹ 5 more variables: name <chr>, pieces <dbl>, us_price <dbl>, quantity <dbl>,
# age_group <chr>library(knitr)